Test Fin

Would love to keep a thread going of what prompts are working for your teams, so we can generate some best practices across the community. 🙌🏻Share away!

We are testing Custom MCP with OAuth for a multi-tenant SaaS use case.Observed behavior: after one admin completes the OAuth flow, all Fin conversations appear to call our MCP server with the same OAuth token, even when the current conversation belongs to another customer/account.Can you confirm:Is Custom MCP OAuth stored at the Intercom workspace / connector level? Does Intercom support per-contact or per-company OAuth grants for Custom MCP? Can Fin trigger an OAuth authorization flow for the current end customer during a conversation? Can Custom MCP tools receive Intercom User Tokens from auth_tokens, or are User Tokens only supported by standard Data connectors? Does every MCP tool call include a stable Intercom workspace/contact/company identifier in metadata or only via configured tool input parameters? Is there a supported way to send a dynamic Authorization header per current Messenger user for Custom MCP? If not, is the recommended design to use standard Data connectors with Us

Hopefully I can describe this as simply as possible to see if this is expected or if anyone has run into this.I have an escalation rule set and live for audience A. I have batch testing setup in the test section and for each batch I set an audience B-H, one at a time or a single one (doesn’t matter). But batch testing is never tested as audience A. For any batch test that I run for any audience B-H, the escalation rule is triggered, meaning that it automatically escalates so that I cannot test my content or other guidance. I must turn off escalation rule for Audience A, test in the batch section as Audience B to get my answers, and then turn on escalation rule for Audience A. This does not seem like desired behavior.If I just skip the batch testing and test directly in my product via the messenger, the Escalation Rule is not triggered and works properly.Does anyone know what could be causing this? Is there another setting I am not aware of?  An example of escalation rule being turned o

I have converted my Conversation attributes for issue types to Fin attributes using the UI workflow. I have an “Other” attribute set with the exact wording that Intercom fin suggested in case it couldn’t detect any of the others from my descriptions. I have them enabled for all audiences. I have a very simple workflow that starts with a user typing and branches to Fin answering. The audience is ‘custom → logged in users’. → What brings you here today? Let customer type → Let Fin handle → If escalated show reply time. When I send fin a message it finds the correct articles and guidance, but there’s no indication it’s detecting any of my attributes as the conversation log does not show the event and the attribute is not set on the conversation details panel. I turned on Urgency attributes to see if it would detect those as a test and it is not detecting them until the ticket is closed, which I think defeats the purpose. But at least I can see a log of when it detects it and it’s setting

Has anyone experienced different responses when using batch test over preview? I feel like it does not have access to my full configuration like its persona. For example, I have renamed my Agent, but it will still refer to itself as Fin.

I want to be able to check if making a change to content will improve Fin’s answer to a question without first having to publish it. Is there anyway to do this? 

Is there a way to mark a question as a test when checking if Fin AI agent is responding as expected after changing guidance? I have had members of my team ask various questions after uploading a “source of truth” to the knowledge base to ensure Fin is responding correctly. Some of these are marked as resolved and others are just sitting in our inbox as unassigned, and I don’t want to mark them as resolved if that is going to create a charge for a test rather than a true customer issue resolution. 

Hi there,We’ve implemented Fin AI (Chat and Email) on our support desk, and it’s been fantastic so far—it’s doing a great job handling first-line queries! 😊However, we’ve noticed a challenge when a customer submits a vague message. Fin will respond with technically correct information, but it’s often not relevant to what the customer truly needs.I’m wondering if it’s possible to improve this by getting Fin to ask clarifying questions before responding. I’ve been advised to set up a new workflow where specific vague questions prompt Fin to ask follow-ups, but trying to predict and account for all the potential vague queries customers might come up with feels inefficient.Is there a better way to manage this? Any advice or insights you could share would be hugely appreciated!Thanks so much

What is the best way to feed FIN AI with Beamer feature requests?  foe example, lead comes in and asks for a feature that is under development.  Unless fin knows about the request, the answer will lead to a conversation.what I am trying to achieve is to streamline the conversation with additional context to increase engagement, conversion and retention.    

Is there a way to automatically send a Slack notification whenever a new lead is captured in Intercom?  (read more) I'd like my team to receive instant alerts in a specific Slack channel whenever someone submits a form or starts a new conversation. Are there any built-in integrations or recommended workflows to set this up?

Is there a way to automatically send a Slack notification whenever a new lead is captured in Intercom? (read more) I’d like my team to receive real-time alerts in a designated Slack channel whenever someone submits a form or starts a new conversation. Are there any built-in integrations or best-practice workflows to set this up?

Will Fin ever have the ability to reply to a customer’s question with a screenshot or potentially a video? It is good at reviewing what we have and describing it but it would be very helpful to share the actual image (especially in a navigation question scenario).

Hi, The feature of "Fix grammar & spelling" is handy, however, when the selected sentence is incomplete (not ended correctly), it does add the missing word and/or punctuation marks to the end of that sentence (Expected); but, it also prefixes the missing word/punctuation to the top of the text!!!Example: It changes"I can assist you in this"to"matterI can assist you in this matter."

Hi,We have been using Intercom for our customer support for several months now and we are exploring AI automation solutions. Initially, we built workflows to handle basic support tickets, but we quickly found this approach to be unsustainable, as it became burdensome to maintain and scale.We also tried Intercom Fin, which we found to be an improvement over workflows. However, it is quite expensive, occasionally provides incorrect answers, and struggles with more complex tickets. With Fin charging $1 per resolution and our support agents resolving tickets at about $0.66 each, we decided to explore alternative solutions.I was tasked with identifying a viable option, so I’ve reviewed nearly all the apps listed under the Automation category in the Intercom App Store.There are approximately 140 apps in the Automation category, and we focused on identifying those that can automatically respond to customer messages. From this list, we found over 20 apps that either offer or claim to offer thi

Hi team,I’m looking into the possibility on FIN collecting information when a customer starts a live chat, and sets the Conversational Attribute to a certain value (‘I want to make a manual booking’).When this attribute has been selected, I’m envisioning that FIN will collect information from the customer and then pass over the compiled list of answers to an agent in the form of a ticket/a conversation, but with little need for the customer to reach out back and forth with the agent. For example:Customer starts chat Customer selects ‘I want to make a manual booking’. FIN answers, but because of Step 2, he has specific instructions to ask for the answers to a list of pre-determined questions (such as, ‘What is the name of the supplier, what dates, what room type, etc...’  FIN then thanks the customer and says that this will be booked for them ASAP, and we will reach out if we need anything else.For step 3, I am struggling to find where we would set up this list of questions that we know

FINs newest feature Guidance is now live in Beta? Are you using it?With such a new feature, that is possible the most powerful and complex, moved to Beta recently I’d love to hear how many of you are using it and how you are all finding it?Lets try share tops tips in the below, so we can all learn from each other.Examples of how you are using it What's working well What's not doing what you expect Anything else that is good to know

When creating public articles, you have four components that can help get them discovered:Title Description Body CollectionAI Agent will ingest this content and attempt to provide a best-fit answer based on its knowledge.However, if you want multiple queries to lead to the same article, it seems there isn’t a direct way to accomplish it other than including wording throughout the title, description, and body such that alternative queries may pick up on that language. ExampleSuppose we have an article:Title: How do I add a payment method? Description: Learn how to associate a card with your account.That’s straightforward enough and satisfies a couple ways that queries might go (“add a payment method,” “associate a card with your account”).But, what if I want these other queries to lead to the same article:How can I pay? Where do I go to make sure you can charge me? I received a notice for non-payment. What do I need to do? I’m seeing an error for collecting an invoice balance. How do I

Hi everyone! We are wanting to integrate intercom with our own software, where information and answers using FIN and our help articles are feed into our product using AI. We report data to our customers and want a way to pair the data presented with information from our help center (when relevant). Perhaps ambitious.. But wondering if anyone has created more indepth integrations with their software in the back end? Thanks in advance for your help!

I’d like to be able to assign a certain collection of Snippets to only be offered for specific audiences/those with specific user tags, much like we are able to set view rules for Help Center articles.  Is this possible for Snippets, or in the works?

Hello,I am lucky enough to be sitting on a lot of emails around 100,000 from conversations that we have had through email. My main goal is to figure out how we've been solving our customers' problems. I’m thinking about using FIN to help make sense of all this data and hopefully teach it to understand how we resolve different issues so that it can make suggestions and learn.I am wondering if anyone has attempted to feed FIN conversations and how that has worked out or if there is a better way of doing this. I may just take the previous year’s worth of emails and attempt to upload as a PDF. I know this data is useful.I have been looking for a way to import the conversations into Intercom but it does not seem possible. If anyone has been in this situation before I would love to hear how you tackled it.I’m really open to suggestions on how to pull this off or if there’s a better way I haven’t thought of.Thanks,Jon

Can Fin AI bot authenticate a user and allow the user to perform certain actions specific to the user?  I’ve explored custom objects and actions but it seems to me that anyone using the Fin AI chatbot would be able to ask questions related to it. For example: Retrieving order info, requesting refunds, listing all my orders/products specific to the logged in user. Thanks 

Hi, Is there a way to let Fin to send a welcome message whenever someone visits our website? Then if the visitor replies, Fin continue talking with him until the visitor chooses “Talk to real person” button.

Right now we’re trying to improve engagement with a segment of our customers who have access to chat with our team. After asking FIN a question, they can select the standard “get more help” reply buttons and they’ll be connected with our team. However, we’re seeing a lot of people drop off after asking FIN a question. They’ll get a question that appears unhelpful and will go submit a ticket rather than live chat with our team. We want to help get those users connected with our team rather than dropping off after FIN and submitting a ticket. Curious if there is anyone here who has ideas or has worked through a similar problem! Any insight would be appreciated!

If Fin CANNOT answer a question, can it shows a editbox and ask the visitor for his email, after the visitor input the email and click “Submit” button, the conversaion will be sent to an email address automatically?

Hi,We have users accessing Fin directly from our application via a chabot window. Is there a way to make Fin accessible directly via Slack so users can ask their questions directly without having to be connected to our platform?Thanks,Paul N.